<h1 id="comfyui-wan-vace-video-outpainting">ComfyUI Wan VACE Video Outpainting</h1><a target="_blank" rel="ugc" href="https://github.com/stuttlepress">Github</a>This is a lightweight, (almost) no custom nodes ComfyUI workflow meant to quickly outpaint a video with Wan VACE and a minimum of fuss. Just load your video and select the new output area.<h2 id="dependencies">Dependencies</h2>My <a target="_blank" rel="ugc" href="https://github.com/stuttlepress/Comfyui-Wan-VACE-Prep">ComfyUI-Wan-VACE-Prep </a>custom node package, v1.0.16 or later, is required for this workflow. It replaces a large amount of awkward spaghetti workflow math, making this lightweight workflow version possible.In ComfyUI Manager, search for Wan VACE Prep or just load the workflow and then visit the Missing tab in Manager.This is a very lightweight package with no dependencies, so it is highly unlikely to break your system, if that is something you worry about.Nodes 2.0 incompatibility: The node this workflow depends on is known to malfunction under ComfyUI's Nodes 2.0 renderer. No fix is planned until ComfyUI publishes node development documentation.<h2 id="configuration-and-models">Configuration and Models</h2>You'll need the Wan VACE model to run the workflow. Select one appropriate for your system below. Aim for a model weight that matches what you use for normal Wan video generation. e.g., If you usually use an fp8 Wan model, try the fp8 VACE model.<ul><li>Wan 2.2 Fun VACE<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/tree/main/split_files/diffusion_models">bf16 and fp8</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/QuantStack/Wan2.2-VACE-Fun-A14B-GGUF/tree/main">GGUF</a></li></ul></li><li>Wan 2.1 VACE<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/resolve/main/split_files/diffusion_models/wan2.1_vace_14B_fp16.safetensors?download=true">fp16</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/QuantStack/Wan2.1_14B_VACE-GGUF/tree/main">GGUF</a></li></ul></li><li>Kijai’s extracted Fun Vace 2.2 modules, for loading along with standard T2V models. <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/discussions/81">Native use examples here</a>.<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Fun/VACE">bf16</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy_GGUF/tree/main/VACE">GGUF</a></li></ul></li></ul><h2 id="changelog">Changelog</h2><ul><li>v1.0.0 Initial release.</li></ul>

Files with SHA256: 4eeb3d342e8a6f3d3577a1d0d9c7dad2d3e1a28ae8a984fe0149ddd8f34f19ef